Decimasan agent- based interdisciplinary framework for decision making in complex systems

Resumo

Decision making for complex systems has traditionally been a complicated task that can be complied using an interdisciplinary approach. It has numerous outcomes and can be applied to manifold domains. Some of them possess an emergency priority: climate change and sustainable development research, studies of public health, ecosystem habitats, epidemiology, and medicine. A great number of overlapping approaches that exist nowadays fail to meet the needs of decision makers, who need to manage complex domains. The main objective of this dissertation is to bring together existing methods for decision support systems creation within a more coherent framework and to provide an interdisciplinary and flexible methodology for modeling complex and systemic domains and policies. This thesis consists of six chapters. In the first one the necessity to work out a new agent-based framework for decision support system creation is argued. In the next chapter the overview of current research in various areas of complex system analysis is presented. The third chapter introduces the DeciMaS framework for creation of agent-based decision making systems in complex domains, and describes extensively the knowledge discovery algorithms and methods used by the framework. The fourth chapter introduces a case study of the DeciMaS application for the assessment of environmental impact upon human health. The fifth chapter outlines the outcomes of the case study for the selected domain, and, finally, the sixth chapter presents the conclusions and foresees the tendencies and directions for future work